© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 81288
    Prev
    Next
    INDEX
    Explanations

    help and assistance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_31_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ષ્
    0.30
    但不
    0.30
     unavoidable
    0.29
     grazed
    0.28
     throats
    0.27
    蛇
    0.27
    sqlalchemy
    0.27
     உண்மைய
    0.26
    Snake
    0.25
    スイ
    0.25
    POSITIVE LOGITS
    可以让
    0.36
     помочь
    0.33
    䡃
    0.33
     ayudará
    0.32
     Helping
    0.32
     દરે
    0.32
     aiutare
    0.31
     demonstrating
    0.31
     showing
    0.31
    helping
    0.31
    Activations Density 0.039%

    No Known Activations